Update sample code links

README.md

@@ -30,7 +30,7 @@ You can use CoPE-B-A4B in three ways:
 
 - **[Zentropi API](https://zentropi.ai/api)** — fastest path, with a generous free tier (no infra required)
 - **Self-hosted vLLM** — for production-scale serving on your own infrastructure
-- **Direct inference in Python** — load via Transformers; see this [Colab notebook](https://colab.research.google.com/drive/1UsILj66wDGjVyO-3gT3cKyaslEskO2Vz) for a working example
+- **Direct inference in Python** — load via Transformers; see this [Colab notebook](https://colab.research.google.com/drive/1JD8OIa3yZYfVbeY81ao03lrvg0aS-6SQ) for a working example
 
 See the [Running the Model](#running-the-model) section below for details on each.
 
@@ -375,7 +375,7 @@ The easiest way to get started with this model is to use it through the [Zentrop
 
 ### via Direct Inference (Python)
 
-To call the model directly via Transformers, see this runnable [Colab notebook](https://colab.research.google.com/drive/1UsILj66wDGjVyO-3gT3cKyaslEskO2Vz). It loads CoPE-B-A4B from the Hub in bf16, applies the proper prompt template, and shows a complete worked example end-to-end.
+To call the model directly via Transformers, see this runnable [Colab notebook](https://colab.research.google.com/drive/1JD8OIa3yZYfVbeY81ao03lrvg0aS-6SQ). It loads CoPE-B-A4B from the Hub in bf16, applies the proper prompt template, and shows a complete worked example end-to-end.
 
 ### via Self-Hosting (vLLM)
 
@@ -393,7 +393,7 @@ If you're currently using CoPE-A-9B and moving to CoPE-B-A4B, three things to kn
 
 ### 1. CoPE-B uses the Gemma-4 chat template
 
-CoPE-B's prompt must be passed through `apply_chat_template` as a user-turn message — the answer comes back as the assistant-turn output. If your CoPE-A code path raw-concatenates the prompt directly, that pattern will not work with CoPE-B. See the [Input Format](#input-format) section above or the runnable [Colab notebook](https://colab.research.google.com/drive/1UsILj66wDGjVyO-3gT3cKyaslEskO2Vz) for the exact pattern.
+CoPE-B's prompt must be passed through `apply_chat_template` as a user-turn message — the answer comes back as the assistant-turn output. If your CoPE-A code path raw-concatenates the prompt directly, that pattern will not work with CoPE-B. See the [Input Format](#input-format) section above or the runnable [Colab notebook](https://colab.research.google.com/drive/1JD8OIa3yZYfVbeY81ao03lrvg0aS-6SQ) for the exact pattern.
 
 Note also that the CoPE-B prompt is leaner than CoPE-A's: there is no `INSTRUCTIONS` header or `ANSWER` footer to include — the chat template's role markers replace them.